docs(obsidian): close tracker item 6; separate the frontmatter tail from the goal

The mirror duplication is resolved and verified. The remaining items are
re-ranked honestly: 1-4 are the frontmatter tail, 2-3 need steward judgement
rather than executor work, and 5 — the capture practice — is the actual goal
and still unstarted.

Flag for whoever designs it: daily-log/ and sessions/ already exist in
00. Compass/00b. Constellations/CapableMind/. Read them first. A capture
practice may already have been attempted here.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JQKeKY9T9d95KpvHwwok8T

claude/memory/project-obsidian-vault-practice.md

@@ -156,7 +156,31 @@ practice would be built from nothing. `00a. _inbox` holds 11 notes.
    workflow to have the important parts of our work captured there"* — the capture practice, the
    thing that would make the vault a practice rather than a tidier archive — **has not been
    designed.** Do not let the frontmatter tail stand in for it.
-6. ⚠ **The `thinking-mirror` write path is ungoverned** (found 2026-08-23). 9 notes carry retired
+6. ✅ **RESOLVED 2026-08-23 — the two mirrors are now one, and it reports.** Steward chose: keep
-   keys again after mirror sync `a58fc00`; any future pass over that subtree is undone on the next
+   `/wrap-up` §7, retire the launchd agent. Done and verified: agent unloaded · plist removed from
-   sync. **Fix the path before re-applying the spec there** — otherwise the work is re-done, which
+   `~/Library/LaunchAgents/` **and from `~/dotfiles/config/capablemind/`** (load-bearing —
-   is what the Prime Directive exists to prevent.
+   `setup-capablemind.sh:135` copies every `*.plist` there into LaunchAgents, so leaving it would
+   resurrect the retired job) · deployed script removed · stale tree deleted after three independent
+   no-loss checks · `/wrap-up` §7 rewritten to name itself the only writer, forbid edits to the
+   derived tree, and report the outcome with its exit code in §8 · spec bumped to **v1.0.1** with
+   principle 7 + §1a declaring mirrored trees out of scope. Commit `f1c91d9`.
+   **End state verified:** live archive 251 files, 0 diff from upstream; stale tree gone; agent gone.
+
+---
+
+## What remains — and what it is worth
+
+Items 1–4 are the **frontmatter tail**: real, bounded, and *not the goal*. Item 5 is the goal.
+
+- **1** is ours and wrong (one bad pointer) — smallest real debt, ~10 minutes once its correct
+  target is decided.
+- **2, 3** are steward-judgement work, not executor work: 73 pointer-form `canonical` values and
+  213 `related` targets need an eye that knows what the notes *mean*.
+- **4** (16 YAML parse errors) has never been in scope and is a session-sized bite.
+- **5 — the capture practice — has still not been started**, and the 2026-08-23 check made it
+  sharper, not smaller: `01. Daily/` holds 11 notes, newest **2025-09-04**, and the Daily Notes
+  plugin is unconfigured. There is no dormant habit to revive.
+  ⚠ Note for whoever designs it: `00. Compass/00b. Constellations/CapableMind/` already contains
+  `daily-log/` and `sessions/` folders. **Read those before designing anything** — a capture
+  practice may already have been attempted here, and re-inventing over it would be the third
+  duplicate mirror in spirit.